In this paper advanced demand modeling approaches are proposed to study intercity passenger booking decision and to segment preferences; all the models are calibrated on internet booking data. Modeling formulations considered include multinomial logit, mixed logit, and latent class models; markets are segmented on trip distances: long, medium, and short. The results show that the following variables: fare price, advance booking (number of day before departure), and departure day of week, can be used as determinants affecting ticket booking. Mixed logit and latent class models are then applied to account for taste heterogeneity. The results indicate that mixed logit model provides the best statistical fit for the long distance and medium distance markets, while the latent class model provides the best statistical fit for the short distance market. Results also indicate that segmenting passengers by booking period provides better fit than segmenting passengers by socioeconomic information.
Mixed Logit and Latent Class Model for Railway Revenue Management. Final Report. (October 2010 - September 2011)
2011
30 pages
Report
Keine Angabe
Englisch
Metropolitan Rail Transportation , Railroad Transportation , Transportation & Traffic Planning , Transportation , Rail transportation , Revenue management , Literature reviews , Economic analysis , Passenger rail systems , Markets , Rapid transit systems , Data analysis , Model formulations , Specifications , Latent Class (LC) Model , Mixed Logit (ML) Model , Passenger choice Models , Advanced demand modeling approaches , Intercity passenger booking decisions
A latent class model for discrete choice analysis: contrasts with mixed logit
Online Contents | 2003
|Reviewers for October 2010-September 2011
AIAA | 2012
Reviewers for October 2010-September 2011
Online Contents | 2012
Reviewers for October 2010 - September 2011
AIAA | 2012